All authors
Claude Skills by fagemx
github.com/fagemx53 skills0 installs77 views
- Agent BrowserAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.Votes: 0GitHub stars: 36
- Arch SpecUse when a concept needs a multi-file design dossier (overview, canonical form, schemas, rules, APIs, slices, demo paths) before it's stable enough for project-plan task decomposition. Not for single-file RFCs, ADRs, or already-stable scopes ready for engineering.Votes: 0GitHub stars: 36
- Code QualityDeep code review and quality analysis for the edda Rust projectVotes: 0GitHub stars: 36
- Code ReviewReview merged code, commit ranges, or codebase paths for correctness, security, architecture, and test risk; use pr-review for open PRsVotes: 0GitHub stars: 36
- CommitComplete pre-commit workflow - run quality checks (format, lint, test) and validate/create conventional commit messagesVotes: 0GitHub stars: 36
- Coord HandoffClean handoff when finishing multi-agent work — summarize, decide, unclaimVotes: 0GitHub stars: 36
- Coord OrchestrateRoute delivery work, and coordinate two or more parallel implementing sessions when a real formation is warrantedVotes: 0GitHub stars: 36
- Coord RequestDetect changes affecting peers and send coordination requestsVotes: 0GitHub stars: 36
- Coord ReviewUse when auditing multi-session coordination or reviewing a delivery candidate before PR or mergeVotes: 0GitHub stars: 36
- Coord SyncSync with peers before starting multi-agent work — see claims, recorded decisions, suggest scopeVotes: 0GitHub stars: 36
- DispatchRETIRED (GH-661) — this skill described a dispatch server from another project that does not exist in this repo. Dispatching a lane here is the `edda dispatch` CLI; see docs/guides/operator-runbook.md §三／§四 and the fleet.lane-launch / fleet.lane-dispatch / fleet.codex-dispatch decisions (`edda ask <key>`).Votes: 0GitHub stars: 36
- Fleet Epic SplitUse when refilling the Fleet feature queue — accepts four input shapes (epic issue, planning doc, ledger decision key, pasted planning summary), then recon → decompose (independence three-question) → dedupe → confirmation table → batch fleet:pending create → cross-references → provenance report. Never writes implementation code.Votes: 0GitHub stars: 36
- Fleet OrchestrateUse when a controller must coordinate two or more agent sessions for parallel review, issue discovery, implementation, verification, dependency conflicts, or unattended progress that must survive context loss or session replacement.Votes: 0GitHub stars: 36
- Fleet Pr LoopUse when driving a fleet PR to LGTM hands-off — a deterministic bash driver alternates an independent fleet-review (gate) and an independent fix pass until LGTM or a round cap, posting each verdict to the PR, then the controller executes a repository standing merge rule when delegated or hands off to the actual merge authority. Reviewer and fixer subagents never merge (GATE-01). Orchestrates fleet-review + a fix pass; reads conventions from the repo's own CLAUDE.md / AGENTS.md.Votes: 0GitHub stars: 36
- Fleet ReviewUse when gating a fleet PR before merge — run REVIEW.md (the repo's executable review spec) end to end against one PR, post the SHA-pinned verdict as a PR comment, and stop. Never fixes, never merges (GATE-01).Votes: 0GitHub stars: 36
- Fleet TriadUse when coordinating engineering work across mixed agent runtimes on this machine — pi terminal sessions as concurrent workers, a separate Claude session as independent verifier, this session as controller — or when you can only reach a target agent via terminal paste, Run-button relay, or cross-session SendMessage (dispatch, monitor, freeze, verdict, merge).Votes: 0GitHub stars: 36
- Fleet WorkerUse when running one lane of the Fleet execution loop — pick a signed-off fleet:ready issue, implement it in an isolated worktree with TDD, open a PR, and stop. Reads conventions from the repo's own CLAUDE.md / AGENTS.md.Votes: 0GitHub stars: 36
- Ground CheckCheck if codebase supports a planned task — what's ready, what's close, what's missingVotes: 0GitHub stars: 36
- Health CheckPeriodic codebase health assessment — 5 dimensions, scorecard, trend trackingVotes: 0GitHub stars: 36
- Intel ScanDual-agent PR intelligence scan — discover contribution opportunities from any repo's PR historyVotes: 0GitHub stars: 36
- Issue ActionResume assigned issue work or resolve issue acceptance, then route through the canonical delivery flowVotes: 0GitHub stars: 36
- Issue CompactConsolidate GitHub issue discussion into clean body for handoffVotes: 0GitHub stars: 36
- Issue CreateCreate GitHub issues from conversation context (general, bug reports, or feature requests)Votes: 0GitHub stars: 36
- Issue IntakeUse when the ready-issue queue is low or a delivery wave is closing, when a defect/finding surfaces mid-session (runtime failure, review discovery, repeated manual step), or when deciding whether an observation deserves a GitHub issue. Also use when authoring any issue body.Votes: 0GitHub stars: 36
- Issue PipelineRoute one or more issue inputs into the canonical delivery flow. Usage: /issue-pipeline 566 567 [--skip-plan] [--no-merge]Votes: 0GitHub stars: 36
- Issue PlanStart working on GitHub issue with deep-dive workflow (research, innovate, plan phases)Votes: 0GitHub stars: 36
- Issue ScanScan codebase, discover work, propose well-scoped issuesVotes: 0GitHub stars: 36
- Parallel WaveUse when two or more ready issues are about to be delivered serially, when authoring or restructuring a conduct wave plan, or when deciding whether concurrent implementation lanes are safe on this workstation (worktree, build lane, review dispatch, merge ordering).Votes: 0GitHub stars: 36
- Path ForwardFind the most unblocking next step given current codebase state and goalsVotes: 0GitHub stars: 36
- Plan DecomposeRETIRED — absorbed by fleet-epic-split. Use fleet-epic-split to turn a planning doc, epic issue, or ledger decision into issues.Votes: 0GitHub stars: 36
- Plan ValidateValidate a plan for gaps by cross-referencing against actual code, call chains, constraints, and test edge casesVotes: 0GitHub stars: 36
- Pr CheckMonitor PR CI pipeline, auto-fix issues, and loop until all checks passVotes: 0GitHub stars: 36
- Pr Review LoopBounded author self-check and fixes before independent current-head review; never a verdict or merge loopVotes: 0GitHub stars: 36
- Pr ReviewPR review: concise, direct, actionableVotes: 0GitHub stars: 36
- Project PlanGenerate a structured planning pack (tracks, tasks, contracts, validation) for any projectVotes: 0GitHub stars: 36
- Project PrinciplesCore architectural and code quality principles that guide all development decisions in the edda projectVotes: 0GitHub stars: 36
- Pull RequestPR lifecycle management - create PRs with proper commits, merge with validation, and manage PR commentsVotes: 0GitHub stars: 36
- Regression GuardSystematic scan → classify → batch fix → add automation to prevent regressionVotes: 0GitHub stars: 36
- Skill AliasCreate command aliases for skills with argumentsVotes: 0GitHub stars: 36
- Skill CraftCreate high-quality Claude Code skills following edda patternsVotes: 0GitHub stars: 36
- Skill TestTest a Claude Code skill — verify it runs, references exist, output is saneVotes: 0GitHub stars: 36
- Spec Review ModesReview architecture specs, RFCs, API docs, design docs, decision-system docs, or any multi-file technical spec stack using three explicit reading modes: (A) quick overview, (B) strict spec audit, and (C) product/architecture critique. Use when the user asks to 看 spec, review docs, 掃一遍架構, 幫我抓矛盾, 做 spec 審查, or wants structured feedback on boundaries, type consistency, lifecycle ownership, API seams, product thickness, or whether a spec feels complete vs actually useful.Votes: 0GitHub stars: 36
- Tech DebtTechnical debt management - scan Rust codebase for bad smells and create tracking issuesVotes: 0GitHub stars: 36
- TestingComprehensive testing patterns and anti-patterns for writing and reviewing testsVotes: 0GitHub stars: 36
- Tracking IssueAnalyze complex problems structurally — map actors, find root causes, create tracking issue with parallel task decompositionVotes: 0GitHub stars: 36
- Verifiable Goal LoopConvert broad goals, long-running projects, learning plans, research tasks, repo modernization, product builds, writing projects, operations work, portfolio prep, or job-search preparation into a proactive verifiable active goal run operating loop. Use when the user wants goal.md/state.md/backlog.md/verifier.md, external stop conditions, sprint/cycle planning, durable progress across long tasks, skill/tool routing, command prompts, autonomy rules, or a reusable method that prevents passive on...Votes: 0GitHub stars: 36
- Edda ConductorMulti-phase AI plan orchestration via edda-conductor. Use when: (1) user wants to run a multi-phase plan, (2) checking conductor status or progress, (3) handling blocked/failed phases (retry, skip, abort), (4) generating plan.yaml from natural language. NOT for: single-task execution (use coding-agent), decision recording (use edda decide), session context (handled by edda bridge).Votes: 0GitHub stars: 36
- Edda WorkflowPost-task notification and draft approval via edda (decision memory). Use when: (1) a coding agent finishes and you need to report results, (2) checking for pending edda drafts that need approval, (3) user says 'approve', 'reject', or asks about draft status. NOT for: recording decisions (use `edda decide` directly), querying past decisions (use `edda ask`), or session context (handled automatically by edda bridge).Votes: 0GitHub stars: 36
- Fleet OrchestrateUse when a controller must coordinate two or more agent sessions for parallel review, issue discovery, implementation, verification, dependency conflicts, or unattended progress that must survive context loss or session replacement.Votes: 0GitHub stars: 36
- Coord DelegateDelegate a whole background job from a project assistant to one distinct controller, bring its done/failed result back to the idle assistant, route a scoped change to the same owner, discover current public status, and resume interrupted workVotes: 0GitHub stars: 36